Employing artificial intelligence and data mining for smart staff recruitment

Other Title(s)

التوظيف الذكي باستخدام الذكاء الاصطناعي و تنقيب البيانات

Dissertant

Abu Rabi, Darin Ali Muhammad

Thesis advisor

al-Fayyumi, Muhammad
Bani Mustafa, Ahmad

University

Isra University

Faculty

Faculty of Information Technology

Department

Department Software Engineering

University Country

Jordan

Degree

Master

Degree Date

2021

Arabic Abstract

عمليه التوظيف هي من أهم القرارات التي يمكن أن تأخذها اي مؤسسة و أكثرها صعوبه, فعمليه التوظيف يجب أن تهدف الى الحصول على الاشخاص الأكثر ملائمة للوظيفة و الأكثر قدره على تحقيق أهداف المؤسسة وأهدافها الاستراتيجيه.

فتوظيف الشخص الغير مناسب قد يؤثر على سمعه المؤسسة، و قد يؤدي إلى اشكالات و نزاعات قانونيه و الي خسائر لايمكن تحملها من قبل المؤسسه.

تقدم هذه الدراسه حلا لهذه المشكله عن طريق تو؛ يف تقنيات الذكاء الاصطناعي في عمليه التوظيف و التي تشمل التعلم الآلي تنقيب البيانات، معالجه اللغات الطبيعيه، و ذلك لتجنب التحيز و اختيار افضل المرشحين المناسبين للوظيفة مما يساعد على زياده فعاليه عمل المؤسسة و ضمان نموها وا زدهارها.

يتضمن الحل المقترح استنباط اهم العوامل و المؤشرات المرتبطة بنجاح الموظفين في المؤسسة، و ذلك من خلال تحليل بيانات الموظفين الحاليين باستخدام نماذج تنقيب البيانات، و من ثم استخدام هذه العوامل و المؤشرات في صياغة الوصف للوظيفة المطلوبه و تحديد متطلباتها و شروط التقدم اليها, ثم مطابقة السير الذاتية للمتقدمين لهذه الوظيفه آليا.

تم في هذه الدراسه تصميم ثلاثه تجارب تطبيقيه لاختبار هذه الطريقة باستخدام مجموعة من البيانات التي تم الحصول عليها من دائرة الاحصاءات العامة الاردنيه باستخدام السجلات الوظيفية ل 529 موظف موزعه على 19 خاصية، حيث تم بناء و نماذج تعلم الي في كل تجربه.

استخلصت هذه الدراسه ان افضل هذه النماذج هو الذي تم بناءه باستخدام K-Nearest Neighbours (KNN) حيث تم الحصول على دقه تصنيف تبلغ %91، يليه النموذج الذي تم بناءه بواسطه Random (%86) Random Committee, (%89) Forest اما في عمليه المطابقة للسير الذاتيه مع المؤشرات المستخلصه من عمليه تنقيب البيانات، فقد تم الحصول على دقه تعادل 80%، علما بأن هذه النتائج هي أفضل من تلك التي تم الحصول عليها في الدرسات المشابهه.

English Abstract

The sample of the study is primarily restricted to Osborne's play, The Entertainer, its characters, society and war's upheaval.

Since the study is an investigation, some references to Osborne's other plays and works are mentioned.

In the end, this study concludes that John Osborne is a social and political dramatist; he depicts the miserable life in the British society after the crisis of Suez and expresses his anger toward politicians.

Osborne uses the decline of the music hall as a metaphor for the decline of the Great Britain, and refers to the suffering of British society through three generations that represent three different stages in the history of Britain.

Post-war era did not only affect the British people, society, economy and power, but it also led to the appearance of different literary movements, new playwrights, and theaters.

Recruiting staff is one of the most difficult and important decisions to be made by the management.

Hiring the wrong candidate would lead to losing valuable potential employees for that may lead to wasting organization resources, profit, and reputation.

It may also expose the employer to troubles and may lead to legal procedures.

In this work, the researcher proposes an intelligent approach for staff recruitment that employs machine learning, data mining, text mining and natural language processing (NLP) for performing smart staff recruitment.

This work aims at enabling employers to utilize artificial intelligence techniques to perform unbiased, efficient, and smart automated recruitment of the best candidates which would help the organization to guarantee growth and prosperity.

The proposed approach involves employing data mining for finding the most important predictors of successful staff performance using the organization's historical data.

A job specification is then automatically generated.

It includes recruitment criteria based on the identified predictors.

Text mining and natural language processing are then applied to match the candidate’s CV to the job specification to screen and shortlist candidates.

The proposed system was applied to a dataset that was acquired from the Jordanian Department of Statistics (JDOS) which consists of profiles of 529 employees that contain 19 features.

The dataset was used for constructing 27 models that were generated in three experiments and used nine machine learning algorithms.

The best performance was achieved using the K-Nearest Neighbours (KNN) which scored 91% classification accuracy, Random Forest with 89% classification accuracy, and Random Committee 86%.

The results were excellent and were also better than most of the results that were reported in similar studies.

As for the results of CVs matching, the performance achieved was 80% using the random forests algorithm.

Main Subjects

Information Technology and Computer Science

No. of Pages

70

Table of Contents

Abstract.

Abstract in Arabic.

Chapter One : Introduction.

Chapter Two : Literature review.

Chapter Three : Data mining.

Chapter Four : Artificial intelligence and machine learning.

Chapter Five : Classi / fication.

Chapter Six : Natural language processing.

Chapter Seven : HR recruitment.

Chapter Eight : Proposed approach.

Chapter Nine : Dataset.

Chapter Ten : Results.

Chapter Eleven : Discussion.

Chapter Twelve : Conclusions and recommendations.

References.

Table of contents.

American Psychological Association (APA)

Abu Rabi, Darin Ali Muhammad. (2021). Employing artificial intelligence and data mining for smart staff recruitment. (Master's theses Theses and Dissertations Master). Isra University, Jordan
https://search.emarefa.net/detail/BIM-1414472

Modern Language Association (MLA)

Abu Rabi, Darin Ali Muhammad. Employing artificial intelligence and data mining for smart staff recruitment. (Master's theses Theses and Dissertations Master). Isra University. (2021).
https://search.emarefa.net/detail/BIM-1414472

American Medical Association (AMA)

Abu Rabi, Darin Ali Muhammad. (2021). Employing artificial intelligence and data mining for smart staff recruitment. (Master's theses Theses and Dissertations Master). Isra University, Jordan
https://search.emarefa.net/detail/BIM-1414472

Language

English

Data Type

Arab Theses

Record ID

BIM-1414472